Papers › Deformable One-shot Face Stylization via DINO Semantic Guidance

Deformable One-shot Face Stylization via DINO Semantic Guidance

1 Mar 2024CVPR 2024 1arXiv:2403.00459archive 2025-07-28

Yang Zhou, Zichong Chen, Hui Huang

This paper addresses the complex issue of one-shot face stylization, focusing on the simultaneous consideration of appearance and structure, where previous methods have fallen short. We explore deformation-aware face stylization that diverges from traditional single-image style reference, opting for a real-style image pair instead. The cornerstone of our method is the utilization of a self-supervised vision transformer, specifically DINO-ViT, to establish a robust and consistent facial structure representation across both real and style domains. Our stylization process begins by adapting the StyleGAN generator to be deformation-aware through the integration of spatial transformers (STN). We then introduce two innovative constraints for generator fine-tuning under the guidance of DINO semantics: i) a directional deformation loss that regulates directional vectors in DINO space, and ii) a relative structural consistency constraint based on DINO token self-similarities, ensuring diverse generation. Additionally, style-mixing is employed to align the color generation with the reference, minimizing inconsistent correspondences. This framework delivers enhanced deformability for general one-shot face stylization, achieving notable efficiency with a fine-tuning duration of approximately 10 minutes. Extensive qualitative and quantitative comparisons demonstrate our superiority over state-of-the-art one-shot face stylization methods. Code is available at https://github.com/zichongc/DoesFS

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

zichongc/doesfs officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

One-Shot Face Stylization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ALIGNAdaptive Instance NormalizationAttentionConvolutionDINODense ConnectionsFeedforward NetworkLayer NormalizationLinear LayerMulti-Head AttentionR1 RegularizationResidual ConnectionSoftmaxStyleGANVision Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections